QwenPaw is a personal AI assistant that runs on a local machine or in the cloud and connects to multiple chat applications. It provides memory, file workspaces, multiple agents, skills, plugins, and integrations with language-model providers and external tools. The catalogue entries are skills that extend its capabilities.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add agentscope-ai/QwenPaw --skill dingtalk_channel-engit clone --depth 1 https://github.com/agentscope-ai/QwenPawWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/agentscope-ai/qwenpaw/dingtalk_channel-en)<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw/dingtalk_channel-en"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw/dingtalk_channel-en/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/agentscope-ai/qwenpaw/dingtalk_channel-en"><img src="https://agentmods.dev/badge/skills/agentscope-ai/qwenpaw/dingtalk_channel-en.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 30 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00069 | $0.02287 |
| Opus 5 | $0.00034 | $0.01144 |
| Sonnet 5 | $0.00014 | $0.00457 |
| Haiku 4.5 | $0.00007 | $0.00229 |
Grade A, and why
dingtalk_channel_connect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- dingtalk_channel_connect — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DingTalk Channel Auto-Connect (Headed Browser)
This skill automates the creation of a DingTalk application and the binding of a QwenPaw channel using a headed browser.
Mandatory Rules
- Must launch in headed browser mode:
{"action": "start", "headed": true}
-
Must pause when a login gate is encountered:
- If the page displays a login screen (e.g., login prompt, QR code login, phone/password login), stop automated operations immediately.
- Clearly prompt the user to log in manually first, then wait for the user to reply with "logged in / continue".
- Do not proceed with subsequent steps until the user confirms.
-
Any application configuration change only takes effect after creating a new version and publishing:
- After configuring bot-related information, you must publish the bot.
- Whether creating a new application or modifying application information (name, description, icon, bot configuration, etc.), you must perform "create new version + publish" at the end.
- Do not claim the configuration is active if publishing has not been completed.
Pre-Execution Confirmation (Must Do First)
Before starting automated clicks, initiate a "configuration confirmation" with the user, clearly informing them of customizable fields, image specifications, and default values. Use the following structured confirmation:
-
Allow the user to customize the following fields:
- Application name
- Application description
- Bot icon image URL or local path
- Bot message preview image URL or local path
-
Clearly state the image specifications (prominently):
- Bot icon: JPG/PNG only,
240*240pxor larger,1:1ratio, under2MB, no rounded corners. - Bot message preview image: format
png/jpeg/jpg, no more than2MB.
- Bot icon: JPG/PNG only,
-
Clearly state the default values (used automatically if the user does not specify):
- Application name:
QwenPaw - Application description:
Your personal assistant - Bot icon:
https://img.alicdn.com/imgextra/i4/O1CN01M0iyHF1FVNzM9qjC0_!!6000000000492-2-tps-254-254.png - Bot message preview image:
https://img.alicdn.com/imgextra/i4/O1CN01M0iyHF1FVNzM9qjC0_!!6000000000492-2-tps-254-254.png
- Application name:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 194 lines · 69 tokens per session scan A bb6e4ebfbb67
dingtalk_channel_connect is a skill published in the GitHub repository agentscope-ai/QwenPaw (34,809 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 2,287 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
browser-setup
A setup guide for connecting Clacky's browser tool to Chrome or Edge. It supports macOS, Linux, and Windows installations used through WSL, and stores the connection settings in a configuration file.
channel-manager
Configure IM platform channels (Feishu, WeCom, Weixin, Discord, Telegram, DingTalk) for openclacky. Uses browser automation for navigation; guides the user to paste credentials and perform UI steps. Trigger on: "channel setup", "setup feishu", "setup wecom", "setup weixin", "setup wechat", "setup discord", "setup…
browser_cdp
Use this skill when the user explicitly wants to connect to a running Chrome browser, scan local CDP ports, specify a cdpport, or share a single browser across multiple agents/tools. By default, browseruse already launches the browser using managed CDP; if the user does not want to expose browser history, cookies, or…
browser_cdp
A guide for connecting browser-control tools to an existing Chrome session through its remote debugging interface. It explains scanning ports, attaching to a browser, choosing a port, sharing a browser, and switching to a more private control mode.
browser_visible
A guide to browseruse launch settings for Chromium-based browsers. It covers visible windows, private control, extra browser start options such as incognito mode or a proxy, and choosing a browser executable path.
browser_visible
Use this skill when the user needs to control the browser launch mode for browseruse. By default, browseruse launches the local Chrome/Chromium using managed CDP; headed controls whether the window is visible, and privatemode controls whether CDP is disabled in favor of Playwright.